Due to the complex process by which electronic health records (EHR) are generated and collected, missing data is a huge challenge when conducting large observational studies using EHR data. Most standard methods to adjust for selection bias due to missing data fail to address the heterogeneous structure of EHR data. Haneuse et al. (2016) proposed a method that considers a modularization of the data provenance, or the sequence of specific decisions or events that lead to observing complete data. Using this framework, one strategy is to combine inverse probability weighting and multiple imputation at different stages to address missingness. We propose an estimator based on this strategy, show that it is consistent and asymptotically Normal, and derive a consistent estimator of the asymptotic variance. A simulation study demonstrates these properties of the proposed estimator, and the variance estimator is compared with Rubin’s standard combining rules for multiple imputation and a bootstrap-based imputation variance estimator.